From 80a75358cf1fe8c4ddd714cabc99817cad32b051 Mon Sep 17 00:00:00 2001 From: bryan Date: Fri, 16 Jan 2026 16:49:42 -0800 Subject: [PATCH] updated readme --- README.md | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 2916577f..f0c7cf34 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # Hive -Hive is an easy way to craete reliable agenst with expanding toolkits. +Hive is the easiest way to create reliable agents that self-adapt.

Hive Banner @@ -15,7 +15,7 @@ Hive is an easy way to craete reliable agenst with expanding toolkits. ## Overview -Hive provides advanced runtime control for your AI agents, enabling you to observe, intervene, and dynamically adjust agent behavior as it executes. By giving you real-time visibility and control, Hive helps you build more reliable AI systems—catching and correcting issues during execution rather than reacting after failures occur. +Build reliable, self-improving AI agents without hardcoding workflows. Define your goal through conversation with a coding agent, and the framework generates a node graph with dynamically created connection code. When things break, the framework captures failure data, evolves the agent through the coding agent, and redeploys. Built-in human-in-the-loop nodes, credential management, and real-time monitoring give you control without sacrificing adaptability. Visit [adenhq.com](https://adenhq.com) for complete documentation, examples, and guides. @@ -57,12 +57,14 @@ docker compose up ## Features -- **Observe** - Real-time visibility into agent execution, decisions, and performance -- **Metrics & Analytics** - Track costs, latency, and token usage with TimescaleDB -- **Cost Control** - Set budgets and policies to manage LLM spending -- **Real-time Events** - WebSocket streaming for live agent monitoring -- **Self-Hostable** - Deploy on your own infrastructure with full control -- **Production-Ready** - Built for scale and reliability +- **Goal-Driven Development** - Define objectives in natural language; the coding agent generates the agent graph and connection code to achieve them +- **Self-Adapting Agents** - Framework captures failures, updates objectives and updates the agent graph +- **Dynamic Node Connections** - No predefined edges; connection code is generated by any capable LLM based on your goals +- **SDK-Wrapped Nodes** - Every node gets shared memory, local RLM memory, monitoring, tools, and LLM access out of the box +- **Human-in-the-Loop** - Intervention nodes that pause execution for human input with configurable timeouts and escalation +- **Real-time Observability** - WebSocket streaming for live monitoring of agent execution, decisions, and node-to-node communication +- **Cost & Budget Control** - Set spending limits, throttles, and automatic model degradation policies +- **Production-Ready** - Self-hostable, built for scale and reliability ## Project Structure